百度google收录数读取器»

«再次开始

    最近在公司网站的时候需要将公司新浪博客的内容在当前网站中显示，用IFRAME肯定不行，不服合网站的风格。于是自己使用了XMLHTTP来获取公司博客列表页中的标题和URL，再依次读取URL中的代码并截取内容部分。主要使用的方法有ASP中的getHTTPPage，spilt。

    点击查看演示

    关键代码：

  <%
 if application("SinaBlog")<>"" then
    response.write application("SinaBlog")
 else
       Function getHTTPPage(url)
       set http=Server.createobject("Microsoft.XMLHTTP")
       Http.open "GET",url,false
       Http.send()
       if Http.readystate<>4 then
       exit function
       end if
       getHTTPPage=bytesToBSTR(Http.responseBody,"utf-8")'此处注意使用utf-8编码
       set http=nothing
       If Err.number<>0 then
       Response.Write "代码获取失败"
       Err.Clear
       End If
       End Function
       Function BytesToBstr(body,Cset)
       dim objstream
       set objstream = Server.CreateObject("adodb.stream")
       objstream.Type = 1
       objstream.Mode =3
       objstream.Open
       objstream.Write body
       objstream.Position = 0
       objstream.Type = 2
       objstream.Charset = Cset
       BytesToBstr = objstream.ReadText
       objstream.Close
       set objstream = nothing
       End Function
       ListUrl="http://blog.sina.com.cn/s/articlelist_1622797951_0_1.html"'新浪博客列表页地址
       if ListUrl="" Then response.write "url is empty":response.end
       startFlag="<div class=""componentContent"">"
       endFlag="<div class=""bottom_blk"">"
       if application("urldata")<>"" Then
         strContent=application("urldata")
        else
         strContent=getHTTPPage(ListUrl)
         application("urldata")=strContent
       end if 
       if strContent="" or instr(strContent,startFlag)<1 Then
         response.write "code get error"
        else
         c1=split(strContent,startFlag)
         c2=split(c1(1),endFlag)
         MainData=c2(0)'内容列表
         aSplitstr="<div class=""manage floatRight""></div>"'文章分割符
         c3=split(MainData,aSplitstr)
         if ubound(c3)>6 then'最多只显示6条
             MaxTitNum=6
         else
            MaxTitNum=ubound(c3)
         end if   
         for i=0 to MaxTitNum'开始分个读取所需数据
         if instr(c3(i),"<div class=""articleTitle_d"">")>0 then'判断是否为所需数据
        c4=split(c3(i),"target=""_blank"">")'读取文章URL
        c5=split(c4(0),"<a href=")
        a_url=replace(c5(1),"""","")'赋值URL
        c6=split(c4(1),"</a>")
        a_tit=c6(0)'赋值文章标题
        c7=split(c4(1),"<span class=""time space_d01"">")
        a_pot=replace(replace(replace(c7(1),"</span></div>",""),"(",""),")","")
        a_body=getHTTPPage(a_url)
        if a_body="" or instr(a_body,"<div class=""articleContent"" id=""articleBody"">")<1 then
       a_con="get content error"
      else
          a_con1=split(a_body,"<div class=""articleContent"" id=""articleBody"">")'分割文章body
       a_con2=split(a_con1(1),"<div class=""toMiniblog"">")
       a_con=replace(replace(a_con2(0),"<p>&nbsp;<wbr></P>",""),"<!--   -->","")'赋值文章内容
     end if  
     application("SinaBlog")=application("SinaBlog")&"<div class=title>"&a_tit&"</div>"&_
    "<div class=content>"&a_con&" <a href="&a_url&" target=_blank>...<b>点击查看全文</b></a></div> <div class=posttime>发表于："&a_pot&"</div>"
     response.write application("SinaBlog") 
         end if
      next     
       end if 
     end if%>